| Abstract Scope |
Agentic AI systems connect large language models to external scientific tools, yet whether and when tool access improves prediction accuracy remains uncharacterized. We present AGAPI (AtomGPT.org API), an open-access platform integrating eight open-source LLMs with 18 REST end points (28 agent tools, 50 web apps) spanning materials databases, force fields, tight-binding band structures, X-ray diffraction, and protein structure. A three-evaluation residual decomposition on JARVIS-Leaderboard electronic-structure test sets separates agent pipeline fidelity from inherited density functional theory functional bias. For bulk modulus and bandgap the agent reproduces JARVIS-DFT entries to numerical precision, so the experimental-reference degradation is functional bias, not agentic malfunction. On memorization-resistant test sets (57 defective supercells, 60 hypothetical compositions), tool-augmented mean absolute error is below 0.005 eV versus 1.25 to 1.86 eV tool-free, confirming tools are indispensable where parametric knowledge is unavailable. We further demonstrate autonomous multistep workflows including 10-operation defect-engineering pipelines. AGAPI is available at https://github.com/atomgptlab/agapi. |